Prospective epidemiological studies involving paired organs
- 1 May 1988
- journal article
- research article
- Published by Wiley in Statistics in Medicine
- Vol. 7 (5) , 619-625
- https://doi.org/10.1002/sim.4780070509
Abstract
Standard methods of analysing survival data or case‐control data normally concern factors affecting a subject as a whole. However, in a study of a condition that might develop in one or both of a pair of bodily organs information on response and on covariates may be available for each separately. This information can be used to investigate whether the presence of a factor on one side is associated with the condition on that same side, and thus leads to more direct evidence concerning aetiology. In this paper methods of analysing data on paired organs are described. The techniques are illustrated using data from a case‐control study of breast cancer, in which the role of breast calcifications was of interest.Keywords
This publication has 11 references indexed in Scilit:
- More on "Biased Selection of Controls for Case-Control Analyses of Cohort Studies"Biometrics, 1986
- Breast cancer prediction and the Wolfe classification of mammogramsPublished by American Medical Association (AMA) ,1985
- Multivariate Generalizations of the Proportional Hazards ModelJournal of the Royal Statistical Society. Series A (General), 1985
- Biased Selection of Controls for Case-Control Analyses of Cohort StudiesBiometrics, 1984
- Rank tests for censored matched pairsBiometrika, 1980
- Retrospective studies and failure time modelsBiometrika, 1978
- Regression Models and Life-TablesJournal of the Royal Statistical Society Series B: Statistical Methodology, 1972
- Note on the sampling error of the difference between correlated proportions or percentagesPsychometrika, 1947